Knowledge Support for Parallel Performance Data Mining

PerformanceOperation implements DeriveMetricOperation PerformanceResult AbstractResult implementsResult implements TrialResult extends extends FIGURE 17: PerfExplorer script object hierarchy. AbstractPerformanceOperation class, and will take one more more input data sets with two or more metrics each, and generate a derived metric representing either the addition, subtraction, multiplication, or division of one metric with the other. Corresponding with the operation hierarchy is the data hierarchy. At the top of the hierarchy is the PerformanceResult interface, which defines basic methods for accessing the profile data within. The abstract implementation of the interface is AbstractResult class, which defines many internal data structures and static constants. The TrialResult class is an example of a class which is a concrete implementation of the abstract class, and provides an object which holds the performance profile data for a given trial, when loaded from PerfDMF. Table 7 shows a list of the available operations. It is important to note that the output from each of the operations is a new object, and the input data objects are effectively immutable, in that they are not changed by the operation. WhilePerformanceOperation class, and will take one more more input data sets with two or more metrics each, and generate a derived metric representing either the addition, subtraction, multiplication, or division of one metric with the other. Corresponding with the operation hierarchy is the data hierarchy. At the top of the hierarchy is the PerformanceResult interface, which defines basic methods for accessing the profile data within. The abstract implementation of the interface is AbstractResult class, which defines many internal data structures and static constants. The TrialResult class is an example of a class which is a concrete implementation of the abstract class, and provides an object which holds the performance profile data for a given trial, when loaded from PerfDMF. Table 7 shows a list of the available operations. It is important to note that the output from each of the operations is a new object, and the input data objects are effectively immutable, in that they are not changed by the operation. While